Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to lists or rankings, particularly in a "Top X" format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weis
    -0.18
    esto
    -0.17
    uso
    -0.16
    æ¶
    -0.16
    est
    -0.15
    ough
    -0.15
    ucci
    -0.15
    erta
    -0.15
    ton
    -0.15
    ieg
    -0.15
    POSITIVE LOGITS
    onym
    0.26
    ical
    0.23
     Ten
    0.20
    iram
    0.20
    onyms
    0.20
    luluk
    0.19
     Picks
    0.19
     Hat
    0.18
    otec
    0.18
    anga
    0.17
    Act Density 0.018%

    No Known Activations